AgentsAugust 31, 2026via InfoQ AI/ML
DoorDash’s Flux Runs 130,000 Engineering Tasks Through Cloud-Based Agents
Why it matters
Agent infrastructure is graduating from experiment to production engineering discipline. DoorDash's Flux demonstrates how to scale agent workloads safely (scoped access, centralized audit) and measure real impact (weekly code reviews, task volume)—a blueprint competitors will copy.
Key signals
- 130,000 engineering tasks automated in one month via Flux cloud platform
- 25,000+ automated code reviews per week
- Migration from developer laptops to cloud-based deployment
- Architecture: Firecracker microVMs, MCP gateway, reusable playbooks, scoped access, centralized auditing
- Multi-invocation surface support for agent workflows
The hook
130,000 tasks in one month. DoorDash moved engineering agents off laptops to production infrastructure — and the playbook is portable.
DoorDash has moved engineering agent workloads from developer laptops to its Flux cloud platform. The platform automated 130,000 engineering tasks in one month and supports more than 25,000 automated code reviews weekly. Flux uses isolated Firecracker microVMs, an MCP gateway, reusable playbooks, an…